Merge branch 'net-improve-netns-handling-in-rtnetlink'

Xiao Liang says:

====================
net: Improve netns handling in rtnetlink

This patch series includes some netns-related improvements and fixes for
rtnetlink, to make link creation more intuitive:

 1) Creating link in another net namespace doesn't conflict with link
    names in current one.
 2) Refector rtnetlink link creation. Create link in target namespace
    directly.

So that

  # ip link add netns ns1 link-netns ns2 tun0 type gre ...

will create tun0 in ns1, rather than create it in ns2 and move to ns1.
And don't conflict with another interface named "tun0" in current netns.

Patch 01 avoids link name conflict in different netns.

To achieve 2), there're mainly 3 steps:

 - Patch 02 packs newlink() parameters into a struct, including
   the original "src_net" along with more netns context. No semantic
   changes are introduced.
 - Patch 03 ~ 09 converts device drivers to use the explicit netns
   extracted from params.
 - Patch 10 ~ 11 removes the old netns parameter, and converts
   rtnetlink to create device in target netns directly.

Patch 12 ~ 13 adds some tests for link name and link netns.

---

Please note there're some issues found in current code:

- In amt_newlink() drivers/net/amt.c:

    amt->net = net;
    ...
    amt->stream_dev = dev_get_by_index(net, ...

  Uses net, but amt_lookup_upper_dev() only searches in dev_net.
  So the AMT device may not be properly deleted if it's in a different
  netns from lower dev.

- In lowpan_newlink() in net/ieee802154/6lowpan/core.c:

    wdev = dev_get_by_index(dev_net(ldev), nla_get_u32(tb[IFLA_LINK]));

  Looks for IFLA_LINK in dev_net, but in theory the ifindex is defined
  in link netns.

And thanks to Kuniyuki for fixing related issues in gtp and pfcp:
https://lore.kernel.org/netdev/20250110014754.33847-1-kuniyu@amazon.com/

v9: https://lore.kernel.org/20250210133002.883422-1-shaw.leon@gmail.com
v8: https://lore.kernel.org/20250113143719.7948-1-shaw.leon@gmail.com
v7: https://lore.kernel.org/20250104125732.17335-1-shaw.leon@gmail.com
v6: https://lore.kernel.org/20241218130909.2173-1-shaw.leon@gmail.com
v5: https://lore.kernel.org/20241209140151.231257-1-shaw.leon@gmail.com
v4: https://lore.kernel.org/20241118143244.1773-1-shaw.leon@gmail.com
v3: https://lore.kernel.org/20241113125715.150201-1-shaw.leon@gmail.com
v2: https://lore.kernel.org/20241107133004.7469-1-shaw.leon@gmail.com
v1: https://lore.kernel.org/20241023023146.372653-1-shaw.leon@gmail.com
====================

Link: https://patch.msgid.link/20250219125039.18024-1-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 176 insertions, 1 deletions

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 8d6116b80cf1..aeb96c085614 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -36,6 +36,7 @@ TEST_PROGS += cmsg_so_priority.sh
 TEST_PROGS += test_so_rcv.sh
 TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh
 TEST_PROGS += netns-name.sh
+TEST_PROGS += link_netns.py
 TEST_PROGS += nl_netdev.py
 TEST_PROGS += rtnetlink.py
 TEST_PROGS += srv6_end_dt46_l3vpn_test.sh
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 5b9baf708950..ab55270669ec 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -107,3 +107,8 @@ CONFIG_XFRM_INTERFACE=m
 CONFIG_XFRM_USER=m
 CONFIG_IP_NF_MATCH_RPFILTER=m
 CONFIG_IP6_NF_MATCH_RPFILTER=m
+CONFIG_IPVLAN=m
+CONFIG_CAN=m
+CONFIG_CAN_DEV=m
+CONFIG_CAN_VXCAN=m
+CONFIG_NETKIT=y
diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py
index 729457859316..8697bd27dc30 100644
--- a/tools/testing/selftests/net/lib/py/__init__.py
+++ b/tools/testing/selftests/net/lib/py/__init__.py
@@ -2,7 +2,7 @@
 
 from .consts import KSRC
 from .ksft import *
-from .netns import NetNS
+from .netns import NetNS, NetNSEnter
 from .nsim import *
 from .utils import *
 from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily, RtnlAddrFamily
diff --git a/tools/testing/selftests/net/lib/py/netns.py b/tools/testing/selftests/net/lib/py/netns.py
index ecff85f9074f..8e9317044eef 100644
--- a/tools/testing/selftests/net/lib/py/netns.py
+++ b/tools/testing/selftests/net/lib/py/netns.py
@@ -1,9 +1,12 @@
 # SPDX-License-Identifier: GPL-2.0
 
 from .utils import ip
+import ctypes
 import random
 import string
 
+libc = ctypes.cdll.LoadLibrary('libc.so.6')
+
 
 class NetNS:
     def __init__(self, name=None):
@@ -29,3 +32,18 @@ class NetNS:
 
     def __repr__(self):
         return f"NetNS({self.name})"
+
+
+class NetNSEnter:
+    def __init__(self, ns_name):
+        self.ns_path = f"/run/netns/{ns_name}"
+
+    def __enter__(self):
+        self.saved = open("/proc/thread-self/ns/net")
+        with open(self.ns_path) as ns_file:
+            libc.setns(ns_file.fileno(), 0)
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        libc.setns(self.saved.fileno(), 0)
+        self.saved.close()
diff --git a/tools/testing/selftests/net/link_netns.py b/tools/testing/selftests/net/link_netns.py
new file mode 100755
index 000000000000..aab043c59d69
--- /dev/null
+++ b/tools/testing/selftests/net/link_netns.py
@@ -0,0 +1,141 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import time
+
+from lib.py import ksft_run, ksft_exit, ksft_true
+from lib.py import ip
+from lib.py import NetNS, NetNSEnter
+from lib.py import RtnlFamily
+
+
+LINK_NETNSID = 100
+
+
+def test_event() -> None:
+    with NetNS() as ns1, NetNS() as ns2:
+        with NetNSEnter(str(ns2)):
+            rtnl = RtnlFamily()
+
+        rtnl.ntf_subscribe("rtnlgrp-link")
+
+        ip(f"netns set {ns2} {LINK_NETNSID}", ns=str(ns1))
+        ip(f"link add netns {ns1} link-netnsid {LINK_NETNSID} dummy1 type dummy")
+        ip(f"link add netns {ns1} dummy2 type dummy", ns=str(ns2))
+
+        ip("link del dummy1", ns=str(ns1))
+        ip("link del dummy2", ns=str(ns1))
+
+        time.sleep(1)
+        rtnl.check_ntf()
+        ksft_true(rtnl.async_msg_queue.empty(),
+                  "Received unexpected link notification")
+
+
+def validate_link_netns(netns, ifname, link_netnsid) -> bool:
+    link_info = ip(f"-d link show dev {ifname}", ns=netns, json=True)
+    if not link_info:
+        return False
+    return link_info[0].get("link_netnsid") == link_netnsid
+
+
+def test_link_net() -> None:
+    configs = [
+        # type, common args, type args, fallback to dev_net
+        ("ipvlan", "link dummy1", "", False),
+        ("macsec", "link dummy1", "", False),
+        ("macvlan", "link dummy1", "", False),
+        ("macvtap", "link dummy1", "", False),
+        ("vlan", "link dummy1", "id 100", False),
+        ("gre", "", "local 192.0.2.1", True),
+        ("vti", "", "local 192.0.2.1", True),
+        ("ipip", "", "local 192.0.2.1", True),
+        ("ip6gre", "", "local 2001:db8::1", True),
+        ("ip6tnl", "", "local 2001:db8::1", True),
+        ("vti6", "", "local 2001:db8::1", True),
+        ("sit", "", "local 192.0.2.1", True),
+        ("xfrm", "", "if_id 1", True),
+    ]
+
+    with NetNS() as ns1, NetNS() as ns2, NetNS() as ns3:
+        net1, net2, net3 = str(ns1), str(ns2), str(ns3)
+
+        # prepare link netnsid  and a dummy link needed by certain drivers
+        ip(f"netns set {net3} {LINK_NETNSID}", ns=str(net2))
+        ip("link add dummy1 type dummy", ns=net3)
+
+        cases = [
+            # source, "netns", "link-netns", expected link-netns
+            (net3, None, None, None, None),
+            (net3, net2, None, None, LINK_NETNSID),
+            (net2, None, net3, LINK_NETNSID, LINK_NETNSID),
+            (net1, net2, net3, LINK_NETNSID, LINK_NETNSID),
+        ]
+
+        for src_net, netns, link_netns, exp1, exp2 in cases:
+            tgt_net = netns or src_net
+            for typ, cargs, targs, fb_dev_net in configs:
+                cmd = "link add"
+                if netns:
+                    cmd += f" netns {netns}"
+                if link_netns:
+                    cmd += f" link-netns {link_netns}"
+                cmd += f" {cargs} foo type {typ} {targs}"
+                ip(cmd, ns=src_net)
+                if fb_dev_net:
+                    ksft_true(validate_link_netns(tgt_net, "foo", exp1),
+                              f"{typ} link_netns validation failed")
+                else:
+                    ksft_true(validate_link_netns(tgt_net, "foo", exp2),
+                              f"{typ} link_netns validation failed")
+                ip(f"link del foo", ns=tgt_net)
+
+
+def test_peer_net() -> None:
+    types = [
+        "vxcan",
+        "netkit",
+        "veth",
+    ]
+
+    with NetNS() as ns1, NetNS() as ns2, NetNS() as ns3, NetNS() as ns4:
+        net1, net2, net3, net4 = str(ns1), str(ns2), str(ns3), str(ns4)
+
+        ip(f"netns set {net3} {LINK_NETNSID}", ns=str(net2))
+
+        cases = [
+            # source, "netns", "link-netns", "peer netns", expected
+            (net1, None, None, None, None),
+            (net1, net2, None, None, None),
+            (net2, None, net3, None, LINK_NETNSID),
+            (net1, net2, net3, None, None),
+            (net2, None, None, net3, LINK_NETNSID),
+            (net1, net2, None, net3, LINK_NETNSID),
+            (net2, None, net2, net3, LINK_NETNSID),
+            (net1, net2, net4, net3, LINK_NETNSID),
+        ]
+
+        for src_net, netns, link_netns, peer_netns, exp in cases:
+            tgt_net = netns or src_net
+            for typ in types:
+                cmd = "link add"
+                if netns:
+                    cmd += f" netns {netns}"
+                if link_netns:
+                    cmd += f" link-netns {link_netns}"
+                cmd += f" foo type {typ}"
+                if peer_netns:
+                    cmd += f" peer netns {peer_netns}"
+                ip(cmd, ns=src_net)
+                ksft_true(validate_link_netns(tgt_net, "foo", exp),
+                          f"{typ} peer_netns validation failed")
+                ip(f"link del foo", ns=tgt_net)
+
+
+def main() -> None:
+    ksft_run([test_event, test_link_net, test_peer_net])
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/net/netns-name.sh b/tools/testing/selftests/net/netns-name.sh
index 6974474c26f3..0be1905d1f2f 100755
--- a/tools/testing/selftests/net/netns-name.sh
+++ b/tools/testing/selftests/net/netns-name.sh
@@ -78,6 +78,16 @@ ip -netns $NS link show dev $ALT_NAME 2> /dev/null &&
     fail "Can still find alt-name after move"
 ip -netns $test_ns link del $DEV || fail
 
+#
+# Test no conflict of the same name/ifindex in different netns
+#
+ip -netns $NS link add name $DEV index 100 type dummy || fail
+ip -netns $NS link add netns $test_ns name $DEV index 100 type dummy ||
+    fail "Can create in netns without moving"
+ip -netns $test_ns link show dev $DEV >> /dev/null || fail "Device not found"
+ip -netns $NS link del $DEV || fail
+ip -netns $test_ns link del $DEV || fail
+
 echo -ne "$(basename $0) \t\t\t\t"
 if [ $RET_CODE -eq 0 ]; then
     echo "[  OK  ]"